Olga Lyashevska - How can machine learning help to predict changes in size of Atlantic herring ?
[22 July 2016 / 2016-07-22]
[Bilbao, Euskadi, Spain]
This talk is a case-study of how Python (Pandas, NumPy, SciKit-learn)
can be implemented to identify the influence of the potential drivers
of a decline in size of Atlantic herring populations using Gradient
Boosting Regression Trees.
A decline in size and weight of Atlantic herring in the Celtic Sea
has been observed since the mid-1980’s. The cause of the decline
remains largely unexplained but is likely to be driven by the
interactive effect of various endogenous and exogenous factors. The
goal of this study is to interrogate a long time-series of biological
data obtained from commercial fisheries from 1959 to 2012. We use
gradient boosting regression trees to identify important variables
underlying changes in growth from various potential drivers, such as:
- Atlantic multidecadal oscillation;
- sea surface temperature;
- zooplankton abundance;
- fishing pressure.
This learning algorithm allows to quantify the influence of the
potential drivers of change with the test error lower when compared to
other supervised learning techniques. The predictor variables
importance spectrum (feature importance) helps to identify the
underlying patterns and potential tipping points while resolving the
external mechanisms underlying observed changes in size and weight of
herring. This analysis is a useful case-study of how Python can be
implemented in academia. The outputs of the analysis are of relevance
to conservation efforts and sustainable fisheries management which
promotes species resistance and resilience.